Add prompts, rag on session + RAG and Prompt

RAG_PDF_WEB.py

@@ -75,6 +75,9 @@ def rag_pdf_web():
     
     option = st.radio("Source", ("A partir de votre site web", "A partir de vos documents entreprise"))
 
+    vectorstore = None
+    chain = None
+    
     if option == "A partir de votre site web":
         url1 = st.text_input("URL 1")
         url2 = st.text_input("URL 2")
@@ -208,4 +211,10 @@ def rag_pdf_web():
                                     renvoie ta réponse en markdown et bien formatée
                                      '''
                     response = chain.invoke(question)
-                    st.markdown(response.content)
+                    st.markdown(response.content)
+
+    if vectorstore and chain:
+        st.success("Le vectorstore et le RAG chain ont été créés avec succès!")
+        return vectorstore, chain
+    else:
+        return None, None

app.py

@@ -17,6 +17,7 @@ from inspirezvous import *
 from collaborons import display_company_selection_for_materiality,display_materiality_matrix
 from documentations import display_documentation
 from RAG_PDF_WEB import rag_pdf_web
+from prompt import get_prompts_list,prompt_execution,execute_prompt
 
 def main():
     st.markdown(":point_left: Cliquez pour vous inspirer", unsafe_allow_html=True)
@@ -24,7 +25,8 @@ def main():
     st.sidebar.title("OPEN DATA & IA au service de la RSE")
     section_principale = st.sidebar.radio(
         "Choisissez votre section",
-        ["Data Bordeaux métropole", "Data bziiit","IA RSE","Documentation"]
+        ["Data Bordeaux métropole", "Data bziiit","IA RSE","Documentation"],
+        index=2
     )
 
     if section_principale == "Data Bordeaux métropole":
@@ -69,11 +71,13 @@ def main():
                 "Matrice de matérialité"
             ]
         )
+
         if ia_mode == "Parties prenantes":
             data, bziiit_data = fetch_data()
             selected_company = display_company_selection_for_materiality(data)
             if selected_company:
                 display_materiality_partiesprenantes(selected_company, data, bziiit_data)
+
         elif ia_mode == "Matrice de matérialité":
             data, bziiit_data = fetch_data()
             selected_company = display_company_selection_for_materiality(data)
@@ -81,10 +85,20 @@ def main():
                 display_materiality_matrix(selected_company, data, bziiit_data)
         
         elif ia_mode == "Audit flash RSE de vos contenus":
-            rag_pdf_web()
+            vectorstore, chain = rag_pdf_web()
+            if vectorstore and chain:
+                st.session_state['vectorstore'] = vectorstore
+                st.session_state['chain'] = chain
         
-        elif ia_mode == "Prompt RSE disponibles" or ia_mode == "Générations de contenus RSE":
-            st.header(ia_mode)
+        elif ia_mode == "Prompt RSE disponibles":
+            get_prompts_list()
+
+        elif ia_mode == "Générations de contenus RSE":
+            st.header("Exécutez un prompt")
+
+            selected_prompt = prompt_execution()
+            if selected_prompt:
+                execute_prompt(selected_prompt)
 
 
     elif section_principale == "Documentation":

data_manager_bziiit.py

@@ -34,6 +34,22 @@ def get_engaged_brands():
         st.error(f"Échec de récupération des marques engagées: {response.text}")
         return []
 
+# Fonction de récupération des prompts
+def get_prompts():
+    url = f"{BASE_URL}/public/prompts"
+    response = requests.get(url)
+    if response.status_code == 200:
+        return response.json()["response"]
+    else:
+        st.error(f"Échec de récupération des marques engagées: {response.text}")
+        return []
+
+def get_prompt_by_id(id):
+    prompts = get_prompts()
+    for prompt in prompts:
+        if prompt.get('id') == id:
+            return prompt
+
 # Fonction consolidant les données labels + projets RSE + marques
 def get_bziiit_data():
     labels = get_labels()

prompt.py

@@ -0,0 +1,68 @@
+import streamlit as st
+import pandas as pd
+from data_manager_bziiit import get_prompts
+from session import get_rag
+
+prompts = [] 
+def get_prompts_list():
+    st.header("Prompts")
+    prompts = get_prompts()
+
+    # Check if prompts is a list of dictionaries
+    if isinstance(prompts, list) and all(isinstance(i, dict) for i in prompts):
+        # Create a DataFrame
+        df = pd.DataFrame(prompts)
+
+        # Check if 'name', 'context', and 'text' are in df columns
+        if 'name' in df.columns and 'context' in df.columns and 'text' in df.columns:
+            # Extract 'name' from 'context' dictionary
+            df['context'] = df['context'].apply(lambda x: x.get('name') if isinstance(x, dict) else x)
+
+            # Get first 50 characters from 'text' and add "..." at the end
+            df['text'] = df['text'].apply(lambda x: x[:50] + "..." if isinstance(x, str) else x)
+
+            # Group by 'context'
+            grouped = df.groupby('context')
+
+            for name, group in grouped:
+                st.subheader(name)  # Display the context name as a subheader
+                for i, row in group.iterrows():
+                    col1, col2, col3, col4 = st.columns((1, 2, 2, 1))
+                    col1.write(i)  # index
+                    col2.write(row['name'])  # name
+                    col3.write(row['text'])  # text
+                    button_phold = col4.empty()  # create a placeholder
+                    do_action = button_phold.button('Show More', key=i)
+                    if do_action:
+                        st.text(prompts[i]['text'])  # Display the full text
+                        button_phold.empty()  # remove button
+        else:
+            st.write("Data does not contain 'name', 'context', and 'text' fields.")
+    else:
+        st.write("Data is not in the expected format (list of dictionaries).")
+
+
+def prompt_execution():
+    prompts = get_prompts()
+
+    selected_prompt = st.selectbox("Choisissez un prompt", prompts, format_func=lambda prompt: prompt['name'])
+    if selected_prompt:
+        return selected_prompt
+    
+    return None
+
+
+def execute_prompt(prompt):
+    vectorstore, chain = get_rag()
+
+    st.header(prompt['name'])
+    st.text(prompt['text'])
+
+    if vectorstore and chain:
+        st.success("Vectorestore et chain trouvés")
+        
+        if st.button("Exécuter le prompt"):
+            with st.spinner("Processing..."):
+                ambition = chain.invoke(prompt['text'])
+                st.markdown("### Réponse :")
+                st.markdown(ambition.content)

session.py

@@ -0,0 +1,10 @@
+import streamlit as st
+
+def get_rag():
+    if 'vectorstore' in st.session_state and 'chain' in st.session_state:
+        vectorstore = st.session_state['vectorstore']
+        chain = st.session_state['chain']
+        
+        return vectorstore, chain
+    else:
+        return None, None